期刊
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
卷 15, 期 7, 页码 3952-3961出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TII.2018.2884211
关键词
Convolutional neural networks (CNNs); face-pose estimation; low-rank learning; multitask learning
类别
资金
- National Natural Science Foundation of China [61622205, 61836002]
- Zhejiang Provincial Natural Science Foundation of China [LY17F020009]
- Fujian Provincial Natural Science Foundation of China [2018J01573]
- Fujian Provincial High School Natural Science Foundation of China [JZ160472]
- Foundation of Fujian Educational Committee [JAT160357, TII-18-1874]
Face-pose estimation aims at estimating the gazing direction with two-dimensional face images. It gives important communicative information and visual saliency. However, it is challenging because of lights, background, face orientations, and appearance visibility. Therefore, a descriptive representation of face images and mapping it to poses are critical. In this paper, we use multimodal data and propose a novel face-pose estimation framework named multitask manifold deep learning ((MDL)-D-2). It is based on feature extractionwith improved convolutional neural networks (CNNs) and multimodal mapping relationship with multitask learning. In the proposed CNNs, manifold regularized convolutional layers learn the relationship between outputs of neurons in a low-rank space. Besides, in the proposed mapping relationship learning method, different modals of face representations are naturally combined by applying multitask learning with incoherent sparse and low-rank learning with a least-squares loss. Experimental results on three challenging benchmark datasets demonstrate the performance of (MDL)-D-2.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据